Rank Documents and Create Embeddings

Provide a query and candidate documents to find the most relevant passages, or convert supplied inputs into vectors.

What to Ask Leina to Do with Jina AI

Copy a prompt, add your details, and send it to Leina in your connected team chat.

Rerank supplied documents against a question and inspect the highest-ranked matches.

Use Jina model [reranker model ID] to rank these documents [documents] for query [question]. Include the top five documents and their relevance scores.

Get Started with Jina AI

  1. Connect Your Account

    Connect a Jina AI API key from the key manager.

  2. Try a Task

    Tell Leina what you need in your team chat. Include the source, destination, and expected result.

    Set Up Leina in Your Chat →
  3. Check the Result

    Review the result and any changes in the connected app.

Supported Jina AI Capabilities

This connection exposes Jina embedding and reranking operations. You supply the model and source inputs; it does not retrieve documents from a knowledge base.

Embeddings and relevance ranking

Generate vectors for supplied inputs or rank documents by their relevance to a query.

View All 2 Actions
  • Create Embeddings
  • Rerank Documents

Visit Provider Website ↗

Frequently Asked Questions

Can reranking include document text?

Yes. Ask to include documents in the result and specify how many top matches you want.

Can I choose the embedding dimensions?

The embedding request accepts dimensions and normalization options where the chosen model supports them.

Do I need to supply the documents?

Yes. Reranking compares the documents included in your request against the query.

Your AI employee for Jina AI

Tell Leina what you need in your team chat. Include the source, destination, and expected result.